← Back to community benchmarks
MiniCPM4-8B
Performance
1k
tokens
208.4
PP tok/s
21.2
TG tok/s
4919
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 208.4 | 21.2 | 4.8 GB | current |
| 4k | 199.2 | 19.9 | 5.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.2 | 1.00× |
| 2× | 41.8 | 1.97× |
| 4× | 53.0 | 2.50× |